Machine learnINg for the rElapse Risk eValuation in Acute Biliary Pancreatitis.

Acute Pancreatitis Clinical Trial

— MINERVA  

Official title:

A Novel Machine Learning Model for the Prediction of Relapse of Acute Biliary Pancreatitis (Machine learnINg for the rElapse Risk eValuation in Acute Biliary Pancreatitis - MINERVA)

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT06124989
• Other study ID #: MINERVA_1
• Status: Not yet recruiting
• Start date: January 1, 2024
• Est. completion date: December 31, 2025

Study information

• Verified date: November 2023
• Source: University of Cagliari
• Contact: Mauro Podda, MD
• Phone: 07051096571
• Email: mauro.podda[@]unica.it
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The MINERVA (Machine learnINg for the rElapse Risk eValuation in Acute biliary pancreatitis) project stems from the need in the clinical practice of taking an operational decision in patients that are admitted to the hospital with a diagnosis of acute biliary pancreatitis. In particular, the MINERVA prospective cohort study aims to develop a predictive score that allows to assess the risk of hospital readmission for patients diagnosed with mild biliary acute pancreatitis using Machine Learning and artificial intelligence.

The objectives of the MINERVA study are to:

1. Propose a novel methodology for the assessment of the risk of relapse in patients with mild biliary acute pancreatitis who did not undergo early cholecystectomy (within 3 to 7 days from hospital admission);

2. Propose a Machine Learning predictive model using a Deep Learning architecture applied to easily collectable data;

3. Validate the MINERVA score on an extensive, multicentric, prospective cohort;

4. Allow national and international clinicians, medical staff, researchers and the general audience to freely and easily access the MINERVA score computation and use it in their daily clinical practice.

The MINERVA score model will be developed on a retrospective cohort of patients (MANCTRA-1, already registered in ClinicalTrials.gov) and will be validated on a novel prospective multicentric cohort. After validation, the MINERVA score will be free and easy to compute instantly for all medical staff; it will be accessible at any time on the MINERVA website and web app, and will provide an immediate and reliable result that can be a clear indication for the best treatment pathway for the clinician and for the patient.

Description:

Acute pancreatitis is the most common pancreatic disease, with a global incidence of 34 cases per 100,000 individuals. This disease counts more than 1.5 million new patients per year worldwide, with a mortality that approaches 1%. Mild biliary acute pancreatitis patients, when admitted to the hospital, can be treated with index, early cholecystectomy (within 3 to 7 days from the acute episode) or conservatively. While conservative treatment can be resolutive, up to 35% of these patients have a relapse within 30 days, and require emergency surgery in a significantly worse overall patient condition, reducing the chances of success. Other than that, relapse dramatically increases the chances of chronic pancreatitis, pancreatic cancer, postoperative complications and overall mortality. Relapse episodes have also an economic impact on healthcare facilities, as a second and longer hospital admission per patient increases the overall medical cost per patient by at least 100%. So far, however, there are no standardised methods to predict relapse of biliary acute pancreatitis in patients who did not undergo early cholecystectomy after the first episode of mild biliary acute pancreatitis.

The MINERVA (Machine learnINg for the rElapse Risk eValuation in Acute biliary pancreatitis) project stems from the need in the clinical practice of taking an operational decision in patients that are admitted to the hospital with a diagnosis of mild acute biliary pancreatitis.

The MINERVA project aims to reach the following objectives and results:

1. Propose a novel methodology for the assessment of the risk of relapse in patients with mild biliary acute pancreatitis who did not undergo early cholecystectomy after the first episode of mild biliary acute pancreatitis;

2. Propose a Machine Learning predictive model using a Deep Learning architecture applied to data easy to collect from patients;

3. Validate the MINERVA score on an extensive, multicentric, prospective cohort;

4. Allow national and international clinicians, medical staff, researchers and the general audience to freely and easily access the MINERVA score computation and use it in their daily clinical practice.

The MINERVA score will provide the clinicians with a validated and standardized assessment of relapse risk that takes into account the personal history, demographic data and laboratory characteristics of each patient. The MINERVA score will be free and easy to compute instantly for all medical staff; it will be accessible at any time on the MINERVA website and web app, and will provide an immediate and reliable result that can be a clear indication for the best treatment pathway for the clinician and for the patient.

The MINERVA score model will be developed on a retrospective cohort of patients (MANCTRA-1, already registered in ClinicalTrials.gov) and will be validated on a novel prospective multicentric cohort.

Retrospective cohort The model development and initial training will be performed on a retrospective cohort of patients (n=692) collected during a preliminary multicentric study, the MANCTRA-1 study (approved by the Ethics Committee of the University of Cagliari Hospital, MANCTRA-1 - NCT04747990, Prot. PG/2021/7108) conducted by the PI (Dr. Mauro Podda) and the University of Cagliari local responsible of the MINERVA project.

Prospective cohort A total of 430 patients will be recruited in the prospective cohort of the MINERVA study.

Methods The MINERVA score will be grounded on a Machine Learning model that will be developed and trained on a retrospective cohort and validated on a prospective cohort of patients.

All model variables will be processed with kernel Principal Component Analysis (kPCA).

The Convex Hull of the scatterplot of the main components will be computed and the smallest rectangle will be extracted. The rectangle will be transformed into a 2d image with a fixed resolution using feature averaging and normalization.

The model will be developed at the University of Naples Federico II by Dr. Daniela Pacella with the Machine Learning expertise and supervision.

To prevent overfitting, the dataset will be split into training set, test set and validation set. Additionally, k-fold cross-validation will be used. The performance of the MINERVA model will be evaluated using the most adopted measures of accuracy, such as precision, recall and AUC (Area Under the ROC Curve). Additionally, its performance will be compared with that achieved using traditional machine learning methods (SVM, ANN). Missing data will be handled with imputation methods.

Variables Age (Years) Sex (Male:Female) Previous episodes of biliary pancreatitis (Yes; No) Admitting speciality (HepatoPancreatoBiliary surgery, General surgery, Internal medicine, Gastroenterology) Body mass index -BMI- (Kg/m2) Clinical history of diabetes (No diabetes; Yes with organ dysfunction; Yes without organ dysfunction) Clinical history of chronic pulmonary disease (Yes; No) Clinical history of hypertension (Yes; No) Clinical history of atrial fibrillation (Yes; No) Clinical history of ischemic heart disease (Yes; No) Clinical history of chronic kidney disease (No; Yes under medications; Yes in permanent renal replacement therapy or in preparation for it) Clinical history of of diseases of the hematopoietic system (Yes; No) Patient on immunosuppressive medications on hospital admission (Yes; No) White Blood Cells -WBC- (cells/mm3) Neutrophils (cells/mm3) Platelets (Plt/mm3) INR (International Normalized Ratio) C-reactive protein -CRP- (mg/L) Aspartate aminotransferase -AST- (U/L) Alanine aminotransferase -ALT- (U/L) Total bilirubin (mg/dL) Conjugated bilirubin (mg/dL) Gamma-glutamil-transpeptidase -GGT- (U/L) Serum amylase (U/L) Serum lipase (U/L) Lactate DeHydrogenase -LDH- (U/L) Choledocholithiasis (Yes; Yes with common bile duct obstruction; No) Cholangitis (Yes; No) ERCP with sphincterotomy (Yes within 24h from hospital admission; Yes within 24-48h from hospital admission; Yes within 48-72h from hospital admission; No) Acute biliary pancreatitis relapse at 30-day, 60-day, 90-day, 1 year.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 430
• Est. completion date: December 31, 2025
• Est. primary completion date: December 31, 2024
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Adult patients (= 18 years old)

• Clinical diagnosis of mild biliary acute pancreatitis (according to the Revised Atlanta Classification)

• Not submitted to cholecystectomy or ERCP/ES (Endoscopic Retrograde CholangioPancreatography/Endoscopic Sphyncterotomy) during the same hospital admission

Exclusion Criteria:

• Acute pancreatitis of etiology other than gallstones;

• Moderately-severe pancreatitis;

• Severe pancreatitis;

• Presence of pancreatic necrosis;

• Pregnant patients;

• Patients not able to sign the informed consent to take part in the study.

Related Conditions & MeSH terms

• Acute Pancreatitis
• Gallstones
• Pancreatitis
• Pancreatitis Biliary
• Pancreatitis Relapsing

Intervention

Diagnostic Test:
• MINERVA Machine Learning model
The MINERVA score for the prediction of the risk of relapse of acute pancreatitis in patients who did not undergo early cholecystectomy after the first episode of acute biliary pancreatitis will be grounded upon a Machine Learning model that takes into account patients' demographic, clinical, and laboratory variables that can be easily collected and recorded at index patient admission.

Locations

Country	Name	City	State
Italy	University of Cagliari, Emergency Surgery Department	Cagliari	CA

Sponsors (3)

Lead Sponsor	Collaborator
University of Cagliari	Università della Campania Luigi Vanvitelli, Università di Napoli Federico II

Country where clinical trial is conducted

Italy, 

References & Publications (23)

Ahmed Ali U, Issa Y, Hagenaars JC, Bakker OJ, van Goor H, Nieuwenhuijs VB, Bollen TL, van Ramshorst B, Witteman BJ, Brink MA, Schaapherder AF, Dejong CH, Spanier BW, Heisterkamp J, van der Harst E, van Eijck CH, Besselink MG, Gooszen HG, van Santvoort HC, Boermeester MA; Dutch Pancreatitis Study Group. Risk of Recurrent Pancreatitis and Progression to Chronic Pancreatitis After a First Episode of Acute Pancreatitis. Clin Gastroenterol Hepatol. 2016 May;14(5):738-46. doi: 10.1016/j.cgh.2015.12.040. Epub 2016 Jan 6. — View Citation

Bagepally BS, Haridoss M, Sasidharan A, Jagadeesh KV, Oswal NK. Systematic review and meta-analysis of gallstone disease treatment outcomes in early cholecystectomy versus conservative management/delayed cholecystectomy. BMJ Open Gastroenterol. 2021 Jul;8(1):e000675. doi: 10.1136/bmjgast-2021-000675. — View Citation

Chen Y, Chen TW, Wu CQ, Lin Q, Hu R, Xie CL, Zuo HD, Wu JL, Mu QW, Fu QS, Yang GQ, Zhang XM. Radiomics model of contrast-enhanced computed tomography for predicting the recurrence of acute pancreatitis. Eur Radiol. 2019 Aug;29(8):4408-4417. doi: 10.1007/s00330-018-5824-1. Epub 2018 Nov 9. — View Citation

Cho JH, Jeong YH, Kim KH, Kim TN. Risk factors of recurrent pancreatitis after first acute pancreatitis attack: a retrospective cohort study. Scand J Gastroenterol. 2020 Jan;55(1):90-94. doi: 10.1080/00365521.2019.1699598. Epub 2019 Dec 10. — View Citation

da Costa DW, Bouwense SA, Schepers NJ, Besselink MG, van Santvoort HC, van Brunschot S, Bakker OJ, Bollen TL, Dejong CH, van Goor H, Boermeester MA, Bruno MJ, van Eijck CH, Timmer R, Weusten BL, Consten EC, Brink MA, Spanier BWM, Bilgen EJS, Nieuwenhuijs VB, Hofker HS, Rosman C, Voorburg AM, Bosscha K, van Duijvendijk P, Gerritsen JJ, Heisterkamp J, de Hingh IH, Witteman BJ, Kruyt PM, Scheepers JJ, Molenaar IQ, Schaapherder AF, Manusama ER, van der Waaij LA, van Unen J, Dijkgraaf MG, van Ramshorst B, Gooszen HG, Boerma D; Dutch Pancreatitis Study Group. Same-admission versus interval cholecystectomy for mild gallstone pancreatitis (PONCHO): a multicentre randomised controlled trial. Lancet. 2015 Sep 26;386(10000):1261-1268. doi: 10.1016/S0140-6736(15)00274-3. — View Citation

Ding N, Guo C, Li C, Zhou Y, Chai X. An Artificial Neural Networks Model for Early Predicting In-Hospital Mortality in Acute Pancreatitis in MIMIC-III. Biomed Res Int. 2021 Jan 28;2021:6638919. doi: 10.1155/2021/6638919. eCollection 2021. — View Citation

Gurusamy KS, Nagendran M, Davidson BR. Early versus delayed laparoscopic cholecystectomy for acute gallstone pancreatitis. Cochrane Database Syst Rev. 2013 Sep 2;(9):CD010326. doi: 10.1002/14651858.CD010326.pub2. — View Citation

Hong WD, Chen XR, Jin SQ, Huang QK, Zhu QH, Pan JY. Use of an artificial neural network to predict persistent organ failure in patients with acute pancreatitis. Clinics (Sao Paulo). 2013 Jan;68(1):27-31. doi: 10.6061/clinics/2013(01)rc01. No abstract available. — View Citation

Hu X, Yang B, Li J, Bai X, Li S, Liu H, Zhang H, Zeng F. Individualized Prediction of Acute Pancreatitis Recurrence Using a Nomogram. Pancreas. 2021 Jul 1;50(6):873-878. doi: 10.1097/MPA.0000000000001839. — View Citation

Loozen CS, Oor JE, van Ramshorst B, van Santvoort HC, Boerma D. Conservative treatment of acute cholecystitis: a systematic review and pooled analysis. Surg Endosc. 2017 Feb;31(2):504-515. doi: 10.1007/s00464-016-5011-x. Epub 2016 Jun 17. — View Citation

Mador BD, Panton ON, Hameed SM. Early versus delayed cholecystectomy following endoscopic sphincterotomy for mild biliary pancreatitis. Surg Endosc. 2014 Dec;28(12):3337-42. doi: 10.1007/s00464-014-3621-8. Epub 2014 Jun 25. — View Citation

Mashayekhi R, Parekh VS, Faghih M, Singh VK, Jacobs MA, Zaheer A. Radiomic features of the pancreas on CT imaging accurately differentiate functional abdominal pain, recurrent acute pancreatitis, and chronic pancreatitis. Eur J Radiol. 2020 Feb;123:108778. doi: 10.1016/j.ejrad.2019.108778. Epub 2019 Dec 11. — View Citation

Nebiker CA, Frey DM, Hamel CT, Oertli D, Kettelhack C. Early versus delayed cholecystectomy in patients with biliary acute pancreatitis. Surgery. 2009 Mar;145(3):260-4. doi: 10.1016/j.surg.2008.10.012. Epub 2009 Feb 1. — View Citation

Riquelme F, Marinkovic B, Salazar M, Martinez W, Catan F, Uribe-Echevarria S, Puelma F, Munoz J, Canals A, Astudillo C, Uribe M. Early laparoscopic cholecystectomy reduces hospital stay in mild gallstone pancreatitis. A randomized controlled trial. HPB (Oxford). 2020 Jan;22(1):26-33. doi: 10.1016/j.hpb.2019.05.013. Epub 2019 Jun 22. — View Citation

Sankaran SJ, Xiao AY, Wu LM, Windsor JA, Forsmark CE, Petrov MS. Frequency of progression from acute to chronic pancreatitis and risk factors: a meta-analysis. Gastroenterology. 2015 Nov;149(6):1490-1500.e1. doi: 10.1053/j.gastro.2015.07.066. Epub 2015 Aug 20. — View Citation

Schmidt M, Sondenaa K, Vetrhus M, Berhane T, Eide GE. A randomized controlled study of uncomplicated gallstone disease with a 14-year follow-up showed that operation was the preferred treatment. Dig Surg. 2011;28(4):270-6. doi: 10.1159/000329464. Epub 2011 Jul 9. — View Citation

Sharma A, Vans E, Shigemizu D, Boroevich KA, Tsunoda T. DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture. Sci Rep. 2019 Aug 6;9(1):11399. doi: 10.1038/s41598-019-47765-6. — View Citation

Stevens CL, Abbas SM, Watters DA. How Does Cholecystectomy Influence Recurrence of Idiopathic Acute Pancreatitis? J Gastrointest Surg. 2016 Dec;20(12):1997-2001. doi: 10.1007/s11605-016-3269-x. Epub 2016 Sep 23. — View Citation

Umans DS, Hallensleben ND, Verdonk RC, Bouwense SAW, Fockens P, van Santvoort HC, Voermans RP, Besselink MG, Bruno MJ, van Hooft JE; Dutch Pancreatitis Study Group. Recurrence of idiopathic acute pancreatitis after cholecystectomy: systematic review and meta-analysis. Br J Surg. 2020 Feb;107(3):191-199. doi: 10.1002/bjs.11429. Epub 2019 Dec 25. — View Citation

Werner J, Hartwig W, Uhl W, Muller C, Buchler MW. Useful markers for predicting severity and monitoring progression of acute pancreatitis. Pancreatology. 2003;3(2):115-27. doi: 10.1159/000070079. — View Citation

Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018 Aug;9(4):611-629. doi: 10.1007/s13244-018-0639-9. Epub 2018 Jun 22. — View Citation

Yuan X, Xu B, Wong M, Chen Y, Tang Y, Deng L, Tang D. The safety, feasibility, and cost-effectiveness of early laparoscopic cholecystectomy for patients with mild acute biliary pancreatitis: A meta-analysis. Surgeon. 2021 Oct;19(5):287-296. doi: 10.1016/j.surge.2020.06.014. Epub 2020 Jul 22. — View Citation

Zhou Y, Ge YT, Shi XL, Wu KY, Chen WW, Ding YB, Xiao WM, Wang D, Lu GT, Hu LH. Machine learning predictive models for acute pancreatitis: A systematic review. Int J Med Inform. 2022 Jan;157:104641. doi: 10.1016/j.ijmedinf.2021.104641. Epub 2021 Nov 10. — View Citation

* Note: There are 23 references in all — Click here to view all references

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Number of patients with recurrence of biliary acute pancreatitis.	The number of patients with recurrence of biliary acute pancreatitis: prediction of risk relapse of acute biliary pancreatitis in patients after a first episode of mild biliary acute pancreatitis (according to the 2012 Revised Atlanta Classification) not submitted to early (within three to seven days from the acute episode) cholecystectomy. This outcome will be reached by the development and validation of a novel risk score.	30-day, 60-day, 90-day, 1-year
Secondary	Accuracy of the MINERVA model.	Accuracy, sensibility, and specificity (AUC, area under the ROC curve) of the MINERVA Machine Learning model compared with other traditional machine learning models previously adopted in literature (such as ANN and SVM) and with statistical models (such as multiple regression).	30-day, 60-day, 90-day, 1-year